© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11942
    Prev
    Next
    INDEX
    Explanations

    positive expressions of strong emphasis or seriousness

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.76
    Попис
    -0.76
     '-':
    -0.66
     @"";
    -0.65
    orszá
    -0.63
    InitVars
    -0.63
    titleMargin
    -0.62
     honnête
    -0.62
     laget
    -0.61
     hurt
    -0.61
    POSITIVE LOGITS
     seriously
    2.34
    seriously
    2.11
     Seriously
    1.80
    Seriously
    1.62
     Literally
    0.68
     literally
    0.54
     severely
    0.53
    literally
    0.53
    Literally
    0.52
     honestly
    0.52
    Activations Density 0.003%

    No Known Activations